初始化项目，由ModelHub XC社区提供模型

Model: finnianx/michel-micro
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,38 @@
+---
+datasets:
+- HuggingFaceFW/fineweb-edu
+- HuggingFaceTB/cosmopedia
+- epfml/FineWeb2-HQ
+language:
+- en
+---
+An ultra-tiny 28 million parameter model trained on 2.6 billion tokens using a custom dataset mixture. Context length of 1024 tokens.
+
+| Dataset | Weight |
+|---|---|
+| `HuggingFaceFW/fineweb-edu` | 50% |
+| `epfml/FineWeb-HQ` | 30% |
+| `HuggingFaceTB/cosmopedia` (stories split) | 20% |
+
+The tokenizer is a basic bpe tokenizer that was trained on a smaller subset of 80_000 samples of this same data mixture with a vocab size of 8000.
+
+This model has not undergone any post-training.
+
+This base model is best suited for fine-tuning on specific tasks. On its own, it is very limited, but it is a pretty flexible foundation for applications such as toxic comment detection or sentiment analysis.
+
+| Benchmark | Metric | Value |
+|---|---|---|
+| ARC-Challenge | Acc | 0.1980 |
+| ARC-Challenge | Acc Norm | 0.2312 |
+| ARC-Easy | Acc | 0.4091 |
+| ARC-Easy | Acc Norm | 0.3859 |
+| BoolQ | Acc | 0.5850 |
+| HellaSwag | Acc | 0.2749 |
+| HellaSwag | Acc Norm | 0.2823 |
+| PIQA | Acc | 0.5963 |
+| PIQA | Acc Norm | 0.5762 |
+| WinoGrande | Acc | 0.4917 |
+| WikiText | Word PPL | 86.6418 |
+| WikiText | Byte PPL | 2.3034 |
+| WikiText | Bits/Byte | 1.2037 |
+| BLIMP (Avg) | Acc | 0.6975 |

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 3,
+  "dtype": "float32",
+  "eos_token_id": 1,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "max_position_embeddings": 1024,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 10,
+  "num_key_value_heads": 2,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.0",
+  "use_cache": false,
+  "vocab_size": 8000
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 3,
+  "eos_token_id": [
+    1
+  ],
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 2,
+  "transformers_version": "5.5.0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:748176b83db44d8efba6331da174456f7f9828dcdbf03d2f46e014408538fde3
+size 113430352

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "eos_token": "<|im_end|>",
+  "is_local": true,
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2af2546568303261d5bec40f5a2a15f79082477b06cb9d77368008eb6d117932
+size 5201